Chipmunk: A systolically scalable 0.9 mm2, 3.08Gop/s/mW @ 1.2 mW accelerator for near-sensor recurrent neural network inference
- Resource Type
- Conference
- Authors
- Conti, Francesco; Cavigelli, Lukas; Paulin, Gianna; Susmelj, Igor; Benini, Luca
- Source
- 2018 IEEE Custom Integrated Circuits Conference (CICC) Custom Integrated Circuits Conference (CICC), 2018 IEEE. :1-4 Apr, 2018
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Engines
Prototypes
Speech recognition
Real-time systems
Google
Memory management
- Language
- ISSN
- 2152-3630
Recurrent neural networks (RNNs) are state-of-the-art in voice awareness/understanding and speech recognition. On-device computation of RNNs on low-power mobile and wearable devices would be key to applications such as zero-latency voice-based human-machine interfaces. Here we present CHIPMUNK, a small (